© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15788
    Prev
    Next
    INDEX
    Explanations

    the word "caught"

    oai_token-act-pair · gemini-2.0-flash

    caught

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -1.74
     itſelf
    -0.82
    ScopeManager
    -0.73
     виправивши
    -0.73
     Theſe
    -0.73
    PhysRevD
    -0.67
     surla
    -0.67
     समीक्षाओं
    -0.66
    enderror
    -0.66
     userManager
    -0.66
    POSITIVE LOGITS
    ,
    0.57
     exactly
    0.53
     Violence
    0.50
    creas
    0.50
     Beispiel
    0.48
    icago
    0.48
    <eos>
    0.47
     violently
    0.47
    Suddenly
    0.46
     ilustrasi
    0.46
    Activations Density 0.334%

    No Known Activations